Towards Context Consistency in a Rule-Based Activity Recognition Architecture

T. A. Nguyen; V. Degeler; R. Contarino; A. Lazovik; D. Bucur; M. Aiello

doi:10.1109/UIC-ATC.2013.97

Towards Context Consistency in a Rule-Based Activity Recognition Architecture

T. A. Nguyen, V. Degeler, R. Contarino, A. Lazovik, D. Bucur, M. Aiello

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

3 Citations (Scopus)

Abstract

Accurate human activity recognition (AR) is crucial for intelligent pervasive environments, e.g., energy-saving buildings. In order to gain precise and fine-grained AR results, a system must overcome partial observability of the environment and noisy, imprecise, and corrupted sensor data. In this work, we propose a rule-based AR architecture that effectively handles multiple-user, multiple-area situations, recognizing real-time office activities. The proposed solution is based on an ontological approach, using low-cost, binary, wireless sensors. We employ context consistency diagrams (CCD) as a key component for fault correction. A CCD is a data structure that provides a mechanism for probabilistic reasoning about the current situation and determines the most probable current situation in the presence of inconsistencies, conflicts, and ambiguities in sensor readings. The implementation of the system and its evaluation in a living lab environment show that the CCD corrects up to 46.8% of sensor data faults, improving overall recognition accuracy by up to 11.1%, thus achieving reliable recognition results from unreliable sensor data.

Original language	English
Title of host publication	2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing
Pages	625-630
Number of pages	6
ISBN (Electronic)	978-1-4799-2482-0
DOIs	https://doi.org/10.1109/UIC-ATC.2013.97
Publication status	Published - 1 Dec 2013
Externally published	Yes
Event	IEEE 10th International Conference on Ubiquitous Intelligence and Computing, UIC 2013 - Vietri sul Mare, Italy Duration: 18 Dec 2013 → 20 Dec 2013 Conference number: 10

Conference

Conference	IEEE 10th International Conference on Ubiquitous Intelligence and Computing, UIC 2013
Abbreviated title	UIC
Country/Territory	Italy
City	Vietri sul Mare
Period	18/12/13 → 20/12/13

Keywords

knowledge based systems
planning (artificial intelligence)
ubiquitous computing
CCD
accurate human activity recognition
context consistency diagrams
data structure
energy-saving buildings
fault correction
intelligent pervasive environments
multiple area situations
multiple user situations
partial observability
probabilistic reasoning
real time office activity recognition
recognition accuracy
rule-based AR architecture
rule-based activity recognition architecture
sensor data faults
sensor readings
unreliable sensor data
wireless sensors
Charge coupled devices
Cognition
Context
Keyboards
Monitoring
Ontologies
Wireless sensor networks
Context-aware computing
activity recognition
context consistency
context reasoning

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/UIC-ATC.2013.97

Cite this

Nguyen, T. A., Degeler, V., Contarino, R., Lazovik, A., Bucur, D., & Aiello, M. (2013). Towards Context Consistency in a Rule-Based Activity Recognition Architecture. In 2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing (pp. 625-630) https://doi.org/10.1109/UIC-ATC.2013.97

@inproceedings{b1a496ee8e3a45f5a90a853e1fce3c6e,

title = "Towards Context Consistency in a Rule-Based Activity Recognition Architecture",

abstract = "Accurate human activity recognition (AR) is crucial for intelligent pervasive environments, e.g., energy-saving buildings. In order to gain precise and fine-grained AR results, a system must overcome partial observability of the environment and noisy, imprecise, and corrupted sensor data. In this work, we propose a rule-based AR architecture that effectively handles multiple-user, multiple-area situations, recognizing real-time office activities. The proposed solution is based on an ontological approach, using low-cost, binary, wireless sensors. We employ context consistency diagrams (CCD) as a key component for fault correction. A CCD is a data structure that provides a mechanism for probabilistic reasoning about the current situation and determines the most probable current situation in the presence of inconsistencies, conflicts, and ambiguities in sensor readings. The implementation of the system and its evaluation in a living lab environment show that the CCD corrects up to 46.8% of sensor data faults, improving overall recognition accuracy by up to 11.1%, thus achieving reliable recognition results from unreliable sensor data.",

keywords = "knowledge based systems, planning (artificial intelligence), ubiquitous computing, CCD, accurate human activity recognition, context consistency diagrams, data structure, energy-saving buildings, fault correction, intelligent pervasive environments, multiple area situations, multiple user situations, partial observability, probabilistic reasoning, real time office activity recognition, recognition accuracy, rule-based AR architecture, rule-based activity recognition architecture, sensor data faults, sensor readings, unreliable sensor data, wireless sensors, Charge coupled devices, Cognition, Context, Keyboards, Monitoring, Ontologies, Wireless sensor networks, Context-aware computing, activity recognition, context consistency, context reasoning",

author = "Nguyen, {T. A.} and V. Degeler and R. Contarino and A. Lazovik and D. Bucur and M. Aiello",

year = "2013",

month = dec,

day = "1",

doi = "10.1109/UIC-ATC.2013.97",

language = "English",

pages = "625--630",

booktitle = "2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing",

note = "IEEE 10th International Conference on Ubiquitous Intelligence and Computing, UIC 2013, UIC ; Conference date: 18-12-2013 Through 20-12-2013",

}

Nguyen, TA, Degeler, V, Contarino, R, Lazovik, A, Bucur, D & Aiello, M 2013, Towards Context Consistency in a Rule-Based Activity Recognition Architecture. in 2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing. pp. 625-630, IEEE 10th International Conference on Ubiquitous Intelligence and Computing, UIC 2013, Vietri sul Mare, Italy, 18/12/13. https://doi.org/10.1109/UIC-ATC.2013.97

Towards Context Consistency in a Rule-Based Activity Recognition Architecture. / Nguyen, T. A.; Degeler, V.; Contarino, R. et al.
2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing. 2013. p. 625-630.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Towards Context Consistency in a Rule-Based Activity Recognition Architecture

AU - Nguyen, T. A.

AU - Degeler, V.

AU - Contarino, R.

AU - Lazovik, A.

AU - Bucur, D.

AU - Aiello, M.

N1 - Conference code: 10

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Accurate human activity recognition (AR) is crucial for intelligent pervasive environments, e.g., energy-saving buildings. In order to gain precise and fine-grained AR results, a system must overcome partial observability of the environment and noisy, imprecise, and corrupted sensor data. In this work, we propose a rule-based AR architecture that effectively handles multiple-user, multiple-area situations, recognizing real-time office activities. The proposed solution is based on an ontological approach, using low-cost, binary, wireless sensors. We employ context consistency diagrams (CCD) as a key component for fault correction. A CCD is a data structure that provides a mechanism for probabilistic reasoning about the current situation and determines the most probable current situation in the presence of inconsistencies, conflicts, and ambiguities in sensor readings. The implementation of the system and its evaluation in a living lab environment show that the CCD corrects up to 46.8% of sensor data faults, improving overall recognition accuracy by up to 11.1%, thus achieving reliable recognition results from unreliable sensor data.

AB - Accurate human activity recognition (AR) is crucial for intelligent pervasive environments, e.g., energy-saving buildings. In order to gain precise and fine-grained AR results, a system must overcome partial observability of the environment and noisy, imprecise, and corrupted sensor data. In this work, we propose a rule-based AR architecture that effectively handles multiple-user, multiple-area situations, recognizing real-time office activities. The proposed solution is based on an ontological approach, using low-cost, binary, wireless sensors. We employ context consistency diagrams (CCD) as a key component for fault correction. A CCD is a data structure that provides a mechanism for probabilistic reasoning about the current situation and determines the most probable current situation in the presence of inconsistencies, conflicts, and ambiguities in sensor readings. The implementation of the system and its evaluation in a living lab environment show that the CCD corrects up to 46.8% of sensor data faults, improving overall recognition accuracy by up to 11.1%, thus achieving reliable recognition results from unreliable sensor data.

KW - knowledge based systems

KW - planning (artificial intelligence)

KW - ubiquitous computing

KW - CCD

KW - accurate human activity recognition

KW - context consistency diagrams

KW - data structure

KW - energy-saving buildings

KW - fault correction

KW - intelligent pervasive environments

KW - multiple area situations

KW - multiple user situations

KW - partial observability

KW - probabilistic reasoning

KW - real time office activity recognition

KW - recognition accuracy

KW - rule-based AR architecture

KW - rule-based activity recognition architecture

KW - sensor data faults

KW - sensor readings

KW - unreliable sensor data

KW - wireless sensors

KW - Charge coupled devices

KW - Cognition

KW - Context

KW - Keyboards

KW - Monitoring

KW - Ontologies

KW - Wireless sensor networks

KW - Context-aware computing

KW - activity recognition

KW - context consistency

KW - context reasoning

U2 - 10.1109/UIC-ATC.2013.97

DO - 10.1109/UIC-ATC.2013.97

M3 - Conference contribution

SP - 625

EP - 630

BT - 2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing

T2 - IEEE 10th International Conference on Ubiquitous Intelligence and Computing, UIC 2013

Y2 - 18 December 2013 through 20 December 2013

ER -

Towards Context Consistency in a Rule-Based Activity Recognition Architecture

Abstract

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this